{"id":"W4309693330","doi":"10.1101/2022.11.20.517285","title":"scFormer: A Universal Representation Learning Approach for Single-Cell Data Using Transformers","year":2022,"lang":"en","type":"preprint","venue":"bioRxiv (Cold Spring Harbor Laboratory)","topic":"Single-cell and spatial transcriptomics","field":"Biochemistry, Genetics and Molecular Biology","cited_by":11,"is_retracted":false,"has_abstract":true,"ca_institutions":"Vector Institute; University of Toronto; University Health Network","funders":"","keywords":"Computer science; Salient; Transformer; Parallels; Artificial intelligence; Deep learning; Machine learning; Engineering","routes":{"ca_aff":true,"ca_fund":false,"ca_venue":false,"about_ca":false,"invisible_to_affiliation_only":false},"retraction":null,"screen":null,"direct_labels":[],"prediction":{"model_version":"codex-gemma-dda1882f352a","candidate_categories":["metaepi_narrow"],"consensus_categories":[],"category_scores_codex":[0.0005875002,0.0005331632,0.0004632528,0.0001845657,0.0004314126,0.0001646743,0.001026126,0.0005392608,0.00002385644],"category_scores_gemma":[0.0001095711,0.0006534727,0.0002537549,0.0002866217,0.0001261138,0.00003244125,0.0006586268,0.0006824842,0.000001323502],"about_ca_system_candidate":false,"about_ca_system_consensus":false,"about_ca_system_score_codex":0.0001957833,"about_ca_system_score_gemma":0.0006485682,"about_ca_topic_candidate":false,"about_ca_topic_consensus":false,"about_ca_topic_score_codex":0.0001262106,"about_ca_topic_score_gemma":0.000002886281,"domain_scores_codex":[0.9967939,0.0001752707,0.0005008905,0.00159805,0.0003368169,0.0005950356],"domain_scores_gemma":[0.9978542,0.00002795802,0.0003732244,0.001323117,0.0002332056,0.0001883326],"domain_codex":null,"domain_gemma":null,"domain_candidate":null,"domain_consensus":null,"study_design_codex":"bench_or_experimental","study_design_gemma":"bench_or_experimental","study_design_scores_codex":[0.0002448838,0.0002982373,0.001973278,0.0004168213,0.0001842171,0.000005872576,0.00001766268,0.008360704,0.9883435,0.00001469255,0.0001311302,0.000009010828],"study_design_scores_gemma":[0.0025808,0.000492879,0.0003462892,0.00008413605,0.0005626341,1.388642e-7,0.0001125297,0.05071907,0.9139551,7.344009e-7,0.02951412,0.001631564],"study_design_candidate":"bench_or_experimental","study_design_consensus":"bench_or_experimental","genre_codex":"empirical","genre_gemma":"empirical","genre_scores_codex":[0.7653604,0.001041289,0.2300979,0.00003134,0.000897934,0.001355739,0.0009596081,0.0001352549,0.0001205387],"genre_scores_gemma":[0.9655132,0.0002862102,0.03310467,0.00007742635,0.0005359646,0.000100476,0.0001476524,0.0002057018,0.00002868762],"genre_candidate":"empirical","genre_consensus":"empirical","teacher_disagreement_score":0.2001528,"threshold_uncertainty_score":0.9995916,"prediction_status":"machine_predicted_unvalidated"},"machine_scores":{"provisional":true,"baseline":true,"maturity_gate_passed":false,"score_opus":0.04754731737166824,"score_gpt":0.2515806998482842,"score_spread":0.204033382476616,"validation_status":"score_only:v0-immature-baseline","note":"Baseline scores from an immature model (maturity gate not passed). Scores rank; they never assert a category."}}